Dev Gets 16 H100s for a Week, Builds Inference Cluster and Deploys Models at Scale

TheZachMueller · x · 2026-08-18

Developer jagaprasanna thanked Zach Mueller and the Lambda team for lending him 16 H100s ($40K worth of compute) for a week. He built an inference cluster from scratch, deployed multiple models and pushed them to production scale, going through the full journey from cluster setup to large-scale deployment.

He is now writing up the experience and plans to publish it, and is also looking for full-time roles in AI infra and inference workload optimization.

Original post →

More from Infra

Infra channel →